alt Hacker NewsAsk HN: What are you working on? (November 2026)
What are you working on? What have you been curious about lately?
Comments
I'm working on 3 products now:
1. FormBeep(https://formbeep.com) at $38 MRR now - A form to Whatsapp tool. Stack is mainly CF workers with Clerk Auth.
2. SlashLink(https://slashlink.app) $0 - A simple pay as you go amazon link localizer. Great for affiliate folks and a cheaper alternative to Genius. Stack is same, CF workers with SQLite(D1)
3. StackStats(https://stackstats.app) $791 - A better advanced analytics app for Substack writers, fully local. I have been writing on Substack for a while now and their analytics suck!
I am working on https://gangway.sh/
I always wanted to quickly deploy small sites and apps for clients and friends.
While developing this, I realized that this also could be ergonomically similar to Claude artifacts for open source harnesses.
I have a few users that I personally know, but hoping this grows to have more users one day. Not getting abandoned any time soon.
Self hostable and easily forkable with a Apache 2 license.
A NetOps oriented benchmark and a network investigation tool designed for llm to ace that benchmark; which sound wrong I know :)
If you are into agentic SRE or networking tools:
https://cloudywithachanceoflatency.net/blog_04-investigative...
The tool is open source, the benchmark itself should also be published soon)
In my free time I'm doing a lot of things, it's a little crazy—an Imperial Rome TTRPG, an archeological research RAG db to fact-check it, a browser-extension agent harness, experimentally training NCM models (eg entity extraction (didn't work), or playing Wesnoth (jury's still out)), US Cartograms (maps with proportionally adjusted areas), and Jug.fyi (a probabilistic distribution calculator).
I have been working on building an agent and workflow builder that converts chats with claude, chatgpt, gemini or any other chat agent into a workflow or autonomous agent. Its live at toolscaled.com
Also built a free apache 2 agent/ project management system: https://github.com/mhalstrom/maximizepm
Essentially I found the key thing with modern ai assisted development the key thing is to manage your own time/ parallelize without having to switch between chat session as much as possible.
Mostly working on my personal project, pi-container[0], for running the pi coding agent in an isolated and more secure container environment.
A networking-over-DNS client and server, in Go. https://sr.ht/~nullenenenen/ShrewDNS/
A bit like iodine in the basic idea, but the execution and network topologies you build with it are different. It's more of a building block; you get your DNS channels represented as UDP endpoints, and take it from there, ie you can run Wireguard over it, or SSH or a SOCKS5 proxy (using quicmux, so over QUIC), or run Mosh straight over DNS if you're crafty.
It has an Android app too! I tried to submit it to F-Droid but they're so swamped in spammy or low-quality apps that they're not taking any brand new apps :-( A sad state of affairs, that.
Cloud save sync between a real Super Nintendo and emulators.
I’ve just got back into hobby electronics after a fifteen year diversion into software. I set up my workbench this week and this is my first project, something I first imagined building twenty years ago!
I spent the weekend wiring the spare controller port to a microcontroller to act as WiFi bridge. I have a flash cart, so I patch the reset vector to a small save sync routine that talks to the microcontroller.
It was especially magical having Claude read from a logic analyser and flash firmware tweaks iteratively. I still got to wield the soldering iron at least.
My 10+ year old SaaS for test prep: https://crucialexams.com/
I recently rebuilt my COVID project, a Steam/online version of the drinking game Kings Cup: https://store.steampowered.com/app/1506610/Kings_Cup_The_onl...
A friend and I have also started working on a restarting/brewery manager game that is not released yet.
I've been slowly working on migrating things to a more well documented setup as I build things. For the longest time I just set stuff up and then.... Hoped for the best. Started with my main authoritative DNS for some of my domains today, still working on some Ansible setups but I have the zones down in Terraform now. Is it overkill? Absolutely. Am I learning stuff? Also yup
https://github.com/Vermeulen-Solutions/baseline
Astro site starter template meant to be used together with agents.
A small team and I are working on Sendery [1], a transactional email platform for product teams. We're trying to fix some of the headaches that come with managing product emails as companies scale: keeping track of hundreds of templates, maintaining consistent designs, coordinating changes between developers and marketing/ops, and managing everything across multiple languages is way more time consuming than it should be.
It's been a fun project to work on since it's been a pain point for myself on many projects, so I'm mostly just trying to solve my own set of problems and hoping other people find it useful too.
I’m working on a document library app for macOS with tagging, collections and user attributes. Unlike other apps that pull files into their own databases or reorganize files into their own folders, Librium indexes files in place, so your existing folder structure stays in tact. It works with folders on your local drive in addition to external and network drives and the cloud. Search works with on-device text extraction and OCR.
It’s currently in Test Flight beta, but I’m planning to have it to App Review this week.
nothing special, nothing too important, just my hobby spomeniks map: https://github.com/mudroljub/spomeniks
I have been working on marketing tools for SMBs. Text message marketing is quite possibly the strongest but most regulated channel for marketing.
Here is the new site design I'm working on: https://getsetreply2.com/
Here is the existing site which will be updated to the above one: https://getsetreply.com/
Building Wishfox [1] for around 6 years. It's a wishlist app with price tracking, groups, secret Santa and more. Recently did a major rebranding, and the mobile app is almost ready for testers.
Then I'm working on improving my two open-source apps, Portfox [2] and Localfox [3]. Portfox shows ports for running services and dev servers, Localfox provides them with .localhost domains with TLS and Cloudflare tunnels.
[1] https://wishfox.app [2] https://github.com/xergic/portfox [3] https://github.com/xergic/localfox
I'm working on a cross-file deterministic drift checker https://github.com/mennanov/blockwatch
The idea is that the source code is annotated with special rules which configure how parts of the code (also configs and docs) depend on each other. This can be done either directly in the source code comments or in a config file blockwatch.toml
This tool is very useful for large codebases that e.g. share constants across programming languages and configs, have docs that should strictly reflect the current state of the code, etc
It uses tree-sitter to parse the source code, 35+ languages are supported.
The project is actively developed, your feedback is welcomed! Thanks!
Euclase: http://euclase.ai - the creative harness for generative AI
Unifying all the various image/video gen (comfyui for local, api for closed) in one cohesive desktop app, with integrated agents to pilot the whole thing (if you want). It's been fun to build and quite fun to use. Technically out in beta and testable, but working on refining onboarding/docs before I try going wider.
Finding a balance between deep enough to satisfy more technical creatives (like me) and less technical ones. Agent integration helps tremendously with the latter.
Got tired of postman being such a resource hog, so I made a native app that does much same thing for iOS and Mac.
Eventually reached parity at around 4mb and added iCloud synch and mcp so I can control my test suites from Claude on my Mac.
Making it available for others to use this week after seeing a lot of people are also feeling done with postman
Still working away on my book (and library book) recommendations service https://leafle.org
It has if nothing else been very useful for me (it has correctly deduced that I would get something out of borrowing Grief is the Thing With Feathers, the Dispossessed, and Cosmicomics, none of which I would have thought of reading). Plus it has been a fun opportunity to play around with LLMs as an interface and a research and reverse engineering tool; as well as Jev for non-user facing quality work like banning crap openrouter providers based on their output before putting it in front of a user.
Most recently I’ve been dropping off flyers for it at a few local libraries in my area.
I'm working on building browser-based learning games that help my 6 yo' to explore and understand small concepts through tiny games https://chalkolate.com
I build it based on what I thought daughter could improve and ideas that my daughter gave. I am currently working on introducing basic electronics.
I started working on a little news aggregator which has kinda spiralled into more of an open web thing. Keeping it open source, and open to feedback on how to better improve it.
I’ve tinkered with some decision model stuff too, and it can do things like identify possible spoilers in comments, or spiciness levels in comment sections. Works with HN, Bluesky, Lemmy, Mastodon, and can import RSS feeds too.
This month I'm working on several projects:
1. Broadcast (https://sendbroadcast.net) - Self hosted email marketing software. Been working on this since 2024 and positive revenue. Releasing v3 this week! :)
2. Render Screenshot (https://renderscreenshot.com) - Screenshot API (very much a scratch my own itch project)
3. Widgetful (https://widgetful.com) - A menubar app for managing multiple Claude Code agent sessions
APIKulture. An alternative to Postman/Insomnia/Bruno.
To be honest, I started this because Postman and Insomnia became forced-corporate-cloud not usable for me anymore, and Bruno lacked a feature I considered fundamental for my workflow.
The feature is to remember the JSONPath expressions between requests, a feature that Bruno has implemented already.
But I created this thing and I'm using it daily since then. C++ and wxWidgets, it uses 40MB of RAM, and it is super fast, instead of the 400MB used by the above mentioned programs.
As I'm working on my regular decision college applications, and since Opus 5.5 released, I was able to polish up Quillium (https://quillium.bryanhu.com) so I can dogfood it for my college applications.
It's a nonlinear writing editor, so I can keep track of all the versions of different words, paragraphs, sentences, or drafts. No more Final_FINAL_v3_essay.docx
For reasons, my team is pretty much limited to Argo Workflows for our CI.
Nothing against Argo Workflows, but I really wanted to get out of the business of building our own CI product on top of it.
So, I’ve been working on this CI “framework” on top of Hera (the Argo Workflows Python SDK, which is really neat) that will hopefully make it easier for our team to build CI pipelines, with CI “primitives.”
It’s called Stagecraft: https://github.com/elliottmoos/stagecraft
I'm launching https://rallyrama.com, a rally time trial game for iOS and Android with retro graphics and cars from the 90s.
I have zero experience in game development. It's unbelievable how far you can go with Claude these days.
My main projects are still Grasshopper https://addons.mozilla.org/en-US/firefox/addon/grasshopper-u...
And Meltdown https://meltdown.merkoba.com/
Grasshopper is a tab manager for Firefox.
Meltdown is a an AI harness made in python and tkinter.
You can check screenshots of it and descriptions in the link.
Also I've been blogging a lot recently on a weight loss blog. I like asking Kimi for reviews on what I write.
3 products:
- https://polygonjs.com/: a design tool to create interactive 3D configurators
- https://polyreprint.com/: a hosting platform for those configurators. See more enterprise-type examples on https://polygonjs.com/configurators
- https://polyreplay.com/: game made with said design tool
Still plugging away on Slopjective-C 3.0 https://github.com/doublemover/Slopjective-C/pull/8278
and many other things
Working on a shared folder that syncs for agents, where you mount your existing data, apply controls / permissions and can monitor whats going on in real time: https://www.filestash.app/agents/, the code is in: https://github.com/mickael-kerjean/fdrive
I've been building RCHIVE [0], a desktop app for cataloging, searching and reorganizing files on your computers and drives.
I've got 30 years worth of poorly-organized junk strewn about various computers, NAS, backups, folders, etc, and every year that passed made it harder and harder to rein it in to something sane. And last year I had one drive start to go out on me, so between all that, and consulting contracts drying up like a shrub in the Gobi, it felt like time to build the tool I always wished I had. Ended up rolling the dice and turning it into a real product too, took about 14 months (mostly full-time) to get from start to launch.
Anyways, it scans many different sources, gives you unified deep search across the entire catalog (drives online or offline), allows you to virtually organize and clean up giant archives of digital stuff, resiliently copies or moves files when you're ready to actually restructure on disk, or just lets you quickly pop in to find something / browse everything with previews, metadata, etc. It works on Windows, Mac or Linux, works offline, has zero telemetry, deletes nothing, and is fully deterministic in operation. So, like, no goofy AI integrations for decision making or classification, everything is predictable and repeatable, you can even run portable versions off of a USB drive if you don't want to install it.
I also have a companion app RCHIVE Examiner [1], which is a free ncdu-like tool to see where the hell all your hard drive space went, and what's hogging it. Currently only in macOS App Store, but Windows and Linux versions are releasing soon.
There are a handful of discrete, decoupled components underlying both apps as well that people might find useful (especially in CLI scenarios) that I'm also planning on releasing gratis as soon as I get a chance to package them up standalone.
Check it out! I'd love any feedback anybody has.
Polishing up a paper on the minimal components, dynamics, and selection of any systems that persists. https://meta-r0ze.github.io/Persistence-Mechanics/Persistenc...
And then testing its completeness against the vacuum under the presumption that the universe persists.
I'm working on Zustri (https://zustri.com), booking and scheduling for therapists and salons. My girlfriend is a therapist and didn't like any of the booking/scheduling software she tried, so I built her one.
I finished the basics a long while ago. Since then I've added an AI agent, a public booking page, and support for multiple staff. Hopefully, I'm launching soon. Currently finishing final touches, gathering feedback and trying to figure out how to market this
Still plugging away on Flopper to build a holistic view of the GPU market including providers, rental prices, vendor information and mostly - specs for GPUs.
Added a way to look at power/flops and new model requirements lately to try and estimate how many GPUs you need to run a certain model: https://flopper.io/tools/llm-gpu-calculator?model=llama-3-3-...
A reimagination of bloodborne as a native VR game. All interactions have been redesigned to feel physical in VR, and combat retuned etc. It feels less like the original and more like a native VR experience now
https://github.com/bldbrne-vr/bldbrne-vr --- https://www.youtube.com/watch?v=doleBBoJL5U
My son is dyslexic. So I built a Chrome text-to-speech and reading tools extension to make it easier for him to get access to written content online (and also to support him at school). It has support for Google Docs and PDFs as well as the web. There are a few of these, but this one tries to stay out of the way, have better tracking, better voices and lower cost. Still more to do on the reading side - writing is next after that.
Aurora Glass, a living aurora animated across your Mac's menu bar.
It doubles as a status light for coding agents. But mostly I just like looking at it.
Free, no account, no permissions: https://aurora.radiantmachines.com
Too many things...
I mostly focus on solving my own problems, and if I find a solution that can serve other people, I sometimes push it out as a product.
1. A watch app for runners that focuses on competing against previous runs, inspired by the rally games of the 90s where you could race your "ghosts"
2. A LEGO deal tracker that focuses on collectors and LEGO investors and is focused on price prediction based on data.
3. A mobile tracker for all the hundreds of components I use when tinkering with physical devices.
...
(Disclaimer: all of them are built using AI-assisted coding, and I wrote almost no code at all, although I have 30+ years of experience as a developer)
A SAT solver in F#. The performance is surprisingly unintuitive, even for unsatisfiable problems.
Serverless Wordpress + MariaDB without requiring plugins or any modifications to customer code: https://www.agiler.io
The serverless MariaDB is important because it can scale to zero, so you have dev sites that cost less than $0.50/mo.
Also added MCP and CLI tooling that exposes all of the infrastructure + WP CLI + DB so agents can develop WP sites... which is nice because you can still use the WP admin interface, while using AI to develop the site, debug it, change pages and posts, etc.
Magic AI - I'm using it as a sanitized kids chatgpt for 7 activities: Story, image creation, chat, reflections, journal, learn and quizzes. Sends me daily summary on Whatsapp.
It started with building pi in the cloud - with pure cloud flare workers. I have it working now, and can spin up - the wrangler agent can fully run it as long as you pass it an inference key, including a file view, a chatgpt like experience, and ability to build and host custom apps. Can use alarms to wake up to do plain language tasks, etc.
Trying to figure out how to package this up, and where this would even be useful for other apps.
Audion https://github.com/audion-lang/audion
I needed a code-first approach for making installations and interactive art. MaxMsp gets messy with very big projects. Python didn't really work well for music making and Tidal/Pi/Sclang are only meant for sound. So I needed something that has bpm synchronized threads, but can draw and do anything else like file IO, networking, hardware control etc. It works quite well now.
Local-first archive for AI conversations for providers without sane exports like Google AI Studio, OpenRouter (including chats), LM Studio, and others, as I couldn't find any chat archive with OpenRouter/Google AI Studio chat support. It supports semantic search, MCP integration, and continuing old conversations with llama.cpp. npx threadshelf https://github.com/ChrystianSchutz/ThreadShelf
Hunting bugs in the Python ecosystem using fuzzers and AI tools I develop. If you have a Python package or extension you'd like analyzed, just let me know.
https://github.com/ReviewToolkits
Writing a Newspeak implementation of the PostgreSQL TCP protocol!. Talking to a GnuCash database from Chrome web browser. Uses my Newspeak TCP library. Both are bare minimum, probably very broken, but I am able to parse a Postgres result set from a simple query.
Here is a one minute video where I print the result data to the console from a Newspeak workspace.
https://buzzpot.app — a shared canvas for agents and projects, which I am evolving into a multiplayer environment for teams.
https://leaflo.app — a CBT journal that I am developing into a library of CBT techniques and mini-courses.
https://plainline.app — an AI presentation service with a focus on text and data, rather than visuals.
https://www.rgbloom.com/
RGBloom: create printed photo books in minutes (UK only for now) for just £10 including delivery. Been working on this for 8 months, recently launched iOS and Android apps to go alongside the web app. Got just a few dozen orders a week atm.
I'm focused on making it privacy first, keeping as little data as possible for as short a time as possible (no accounts, you don't even need to provide an email address, and if you do it's wiped in 30 days). And transparent pricing: not getting hit with large delivery fees at checkout, and no discounts just honest prices.